Read economic evidence
Ask what changed, what was measured and what can be inferred.
Your route through the ideas
- Correlation
A statistical description of how variables move together, not proof that one causes the other.
- Causation
A change in one factor produces a change in another, assessed against what would have happened otherwise.
- Selection bias
Distortion arising when the observed sample or treatment groups differ systematically in relevant ways.
- Regression
A method for modelling how an outcome varies with one or more explanatory variables.
- Omitted variable bias
Bias in a regression coefficient when an omitted relevant factor is correlated with an included explanatory variable.
- Confidence interval
An interval produced by a method with a stated long-run coverage rate under its assumptions.
- Randomised experiment
A study assigning treatment by chance to make groups comparable in expectation.
- External validity
The extent to which a study’s findings apply to other people, settings or times.